- Leveraging Blogging Activity on Tumblr to Infer Demographics and Interests of Users for Advertising Purposes
Mihajlo Grbovic, Vladan Radosavljevic, Nemanja Djuric, Narayan Bhamidipati, Ananth Nagarajan
abstract
As one of the leading platforms for creative content, Tumblr offers advertisers a unique way of creating brand identity. Advertisers can tell their story through images, animation, text, music, video and more, and they can promote that content by sponsoring it to appear as an advertisement in the streams of Tumblr users. In this paper, we present a framework that enabled one of the key targeted advertising components for Tumblr, specifically, gender and interest targeting. We describe the main challenges involved in the development of the framework, which include the creation of a ground truth for training gender prediction models, as well as mapping Tumblr content to an interest taxonomy. For purposes of inferring user interests, we propose a novel semi-supervised neural language model for categorization of Tumblr content (i.e., post tags and post keywords). The model was trained on a large-scale data set consisting of 6.8 billion user posts, with a very limited amount of categorized keywords, and was shown to have superior performance over the baseline models. We successfully deployed gender and interest targeting capability in Yahoo production systems, delivering inference for users that covers more than 90% of the daily activities on Tumblr. Online performance results indicate advantages of the proposed approach, where we observed a 20% increase in user engagement with sponsored posts in comparison to untargeted campaigns.
bibtex
@InProceedings{{microposts2016_grbovic,
author = {Mihajlo Grbovic, Vladan Radosavljevic, Nemanja Djuric, Narayan Bhamidipati, Ananth Nagarajan},
title = {{Leveraging Blogging Activity on Tumblr to Infer Demographics and Interests of Users for Advertising Purposes}},
crossref = {proc_microposts2016@www2016},
pages = {2--11},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {As one of the leading platforms for creative content, Tumblr offers advertisers a unique way of creating brand identity. Advertisers can tell their story through images, animation, text, music, video and more, and they can promote that content by sponsoring it to appear as an advertisement in the streams of Tumblr users. In this paper, we present a framework that enabled one of the key targeted advertising components for Tumblr, specifically, gender and interest targeting. We describe the main challenges involved in the development of the framework, which include the creation of a ground truth for training gender prediction models, as well as mapping Tumblr content to an interest taxonomy. For purposes of inferring user interests, we propose a novel semi-supervised neural language model for categorization of Tumblr content (i.e., post tags and post keywords). The model was trained on a large-scale data set consisting of 6.8 billion user posts, with a very limited amount of categorized keywords, and was shown to have superior performance over the baseline models. We successfully deployed gender and interest targeting capability in Yahoo production systems, delivering inference for users that covers more than 90% of the daily activities on Tumblr. Online performance results indicate advantages of the proposed approach, where we observed a 20% increase in user engagement with sponsored posts in comparison to untargeted campaigns.},
url = {http://ceur-ws.org/Vol-1691/paper_15.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 11:00 - 11:30 BEST PAPER
ClaimFinder: A Framework for Identifying Claims in Microblogs
Wee Yong Lim, Mong Li Lee, Wynne Hsu
abstract
Twitter is a microblogging platform that allows users to post public short messages. Posts shared by users pertaining to real-world events or themes can provide a rich on-theground live update of the events for the beneffit of everyone. Unfortunately, the posted information may not be all credible and rumours can spread over this platform. Existing credibility assessment work have focused on identifying features for discriminating the credibility of messages at the tweet level. However, they do not handle tweets that contain multiple pieces of information, each of which may have different level of credibility. In this work, we introduce the notion of a claim based on subject and predicate terms, and propose a framework to identify claims from a corpus of tweets related to some major event or theme. Speciffically, we draw upon work done in open information extraction to extract from tweets, tuples that comprises of subjects and their predicate. Then we cluster these tuples to identify claims such that each claim refers to only one aspect of the event. Tweets corresponding to the tuples in each cluster serve as evidence supporting subsequent credibility assessment task. Extensive experiments on two real world datasets shows the ectiveness of the proposed approach in identifying claims.
bibtex
@InProceedings{{microposts2016_lim,
author = {Lim, Wee Yong and Lee, Mong Li and Hsu, Wayne},
title = {{ClaimFinder: A Framework for Identifying Claims in Microblogs}},
crossref = {proc_microposts2016@www2016},
pages = {13--20},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {Twitter is a microblogging platform that allows users to post public short messages. Posts shared by users pertaining to real-world events or themes can provide a rich on-theground live update of the events for the beneffit of everyone. Unfortunately, the posted information may not be all credible and rumours can spread over this platform. Existing credibility assessment work have focused on identifying features for discriminating the credibility of messages at the tweet level. However, they do not handle tweets that contain multiple pieces of information, each of which may have different level of credibility. In this work, we introduce the notion of a claim based on subject and predicate terms, and propose a framework to identify claims from a corpus of tweets related to some major event or theme. Speciffically, we draw upon work done in open information extraction to extract from tweets, tuples that comprises of subjects and their predicate. Then we cluster these tuples to identify claims such that each claim refers to only one aspect of the event. Tweets corresponding to the tuples in each cluster serve as evidence supporting subsequent credibility assessment task. Extensive experiments on two real world datasets shows the ectiveness of the proposed approach in identifying claims.},
url = {http://ceur-ws.org/Vol-1691/paper_01.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 11:30 - 12:00
Birds of a Feather also Tweet: Computational Techniques to Understand User Communities in Social Networks
David Burth Kurka, Alan Godoy, Fernando J. Von Zuben
abstract
The study of social systems shows that there is a relationship of mutual influence between social connections and individual behavior, known as homophily. In this work, we developed a methodology to allow the analysis of interests of groups of users in Twitter network, based on automatic community detection and tweets ranking. The techniques presented reveal evidences that the presence of communities is related to topic specialization, and allow the characterization of elaborate profiles of groups of users based only on their location on the network.
bibtex
@InProceedings{{microposts2016_kurka,
author = {Kurka, David Burth and Godoy, Alan and Von Zuben, Fernando J.},
title = {{Birds of a Feather also Tweet: Computational Techniques to Understand User Communities in Social Networks}},
crossref = {proc_microposts2016@www2016},
pages = {21--27},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {The study of social systems shows that there is a relationship of mutual influence between social connections and individual behavior, known as homophily. In this work, we developed a methodology to allow the analysis of interests of groups of users in Twitter network, based on automatic community detection and tweets ranking. The techniques presented reveal evidences that the presence of communities is related to topic specialization, and allow the characterization of elaborate profiles of groups of users based only on their location on the network.},
url = {http://ceur-ws.org/Vol-1691/paper_05.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 14:00 - 14:15
CEOs on Twitter
Alex Jeongwoo Oh, Pramuan Bunkanwanicha
abstract
We observe many CEOs of big companies as easily as movie stars or sports players on Twitter. Why do they appear on social media and what would be the effect of their Twitter network on the corporate performance and shareholder benefit? This study explores big company CEOs on Twitter. We identify Twitterusing CEOs and examine the impact of their social media activity on the corporate performance. While academic literatures have studied the performance of publicly well-known CEOs mainly with media coverage, we focus more on the big company CEOs on the social media and test its effect on the corporate performance. We discovered the determinants of Twitter status of CEOs, in terms of personal attributes, company attributes and industry. We also found the positive impact of Twitter on corporate performance, contrary to previous evidences of negative effect.
bibtex
@InProceedings{{microposts2016_oh,
author = {Jeongwoo Oh, Alex and Bunkanwanicha, Pramuan},
title = {{CEOs on Twitter}},
crossref = {proc_microposts2016@www2016},
pages = {46--48},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {We observe many CEOs of big companies as easily as movie stars or sports players on Twitter. Why do they appear on social media and what would be the effect of their Twitter network on the corporate performance and shareholder benefit? This study explores big company CEOs on Twitter. We identify Twitterusing CEOs and examine the impact of their social media activity on the corporate performance. While academic literatures have studied the performance of publicly well-known CEOs mainly with media coverage, we focus more on the big company CEOs on the social media and test its effect on the corporate performance. We discovered the determinants of Twitter status of CEOs, in terms of personal attributes, company attributes and industry. We also found the positive impact of Twitter on corporate performance, contrary to previous evidences of negative effect.},
url = {http://ceur-ws.org/Vol-1691/paper_04.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 14:15 - 14:30
Studying the Role of Elites in U.S. Political Twitter Debates
Sebastian Stier
abstract
Because of their ever-growing importance, elite actors from the political sphere and news media have integrated social network sites and especially Twitter into their communication strategies. However, the extent of these adaptation processes is not yet fully understood. This article presents lists of U.S. actors from politics, news media and government. As an exploratory analysis, the influence of elites in U.S. political Twitter debates is investigated by applying basic measures of Twitter influence to two test datasets.
bibtex
@InProceedings{{microposts2016_stier,
author = {Stier, Sebastian},
title = {{Studying the Role of Elites in U.S. Political Twitter Debates}},
crossref = {proc_microposts2016@www2016},
pages = {43--45},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {Because of their ever-growing importance, elite actors from the political sphere and news media have integrated social network sites and especially Twitter into their communication strategies. However, the extent of these adaptation processes is not yet fully understood. This article presents lists of U.S. actors from politics, news media and government. As an exploratory analysis, the influence of elites in U.S. political Twitter debates is investigated by applying basic measures of Twitter influence to two test datasets.},
url = {http://ceur-ws.org/Vol-1691/paper_08.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 14:45 - 14:55
UniMiB: Entity Linking in Tweets using Jaro-Winkler Distance, Popularity and Coherence
Davide Caliano, Elisabetta Fersini, Pikakshi Manchanda, Matteo Palmonari, Enza Messina
abstract
This paper summarizes the participation of UNIMIB team in the Named Entity rEcognition and Linking (NEEL) Challenge in #Microposts2016. In this paper, we propose a knowledge-based approach for identifying, and linking named entities from tweets. The named entities are, further, classiffied using evidence provided by our entity linking algorithm and type-casted into Microposts categories. Our approach achieves significant performance for named entity classiffication and linking.
bibtex
@InProceedings{{microposts2016_caliano,
author = {Caliano, Davide and Fersini, Elisabeta and Manchanda, Pikakshi and Palmonari, Matteo and Messina, Enza},
title = {{UniMiB: Entity Linking in Tweets using Jaro-Winkler Distance, Popularity and Coherence }},
crossref = {proc_microposts2016@www2016},
pages = {70--72},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {This paper summarizes the participation of UNIMIB team in the Named Entity rEcognition and Linking (NEEL) Challenge in #Microposts2016. In this paper, we propose a knowledge-based approach for identifying, and linking named entities from tweets. The named entities are, further, classiffied using evidence provided by our entity linking algorithm and type-casted into Microposts categories. Our approach achieves significant performance for named entity classiffication and linking.},
url = {http://ceur-ws.org/Vol-1691/paper_12.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 14:55 - 15:05
Kanopy4Tweets: Entity Extraction and Linking for Twitter
Pablo Torres-Tramón, Hugo Hromic, Brian Walsh, Buhareh R. Heravi, Conor Hayes
abstract
Named Entity extraction and Linking (NEEL) from text is an essential task in many Natural Language Processing (NLP) applications because it enables a better understanding of the content. However in the context of Social Media, NEEL is challenging due to the higher level of writing mistakes, fast language dynamics and often lack of context. To this end, we adapted Kanopy – an unsupervised graph-based topic disambiguation system – to be used for the task of NEEL in the domain of Twitter, a fast-paced micro-blogging platform. We describe the design of our solution and report the results obtained by our system using the official corpus of Tweets for the NEEL 2016 Challenge.
bibtex
@InProceedings{{microposts2016_torres,
author = {Torres-Tramon, Pablo and Hromic, Hugo and Walsh, Brian and Heravi, Bahareh R. and Hayes Conor},
title = {{Kanopy4Tweets: Entity Extraction and Linking for Twitter}},
crossref = {proc_microposts2016@www2016},
pages = {64--66},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {Named Entity extraction and Linking (NEEL) from text is an essential task in many Natural Language Processing (NLP) applications because it enables a better understanding of the content. However in the context of Social Media, NEEL is challenging due to the higher level of writing mistakes, fast language dynamics and often lack of context. To this end, we adapted Kanopy – an unsupervised graph-based topic disambiguation system – to be used for the task of NEEL in the domain of Twitter, a fast-paced micro-blogging platform. We describe the design of our solution and report the results obtained by our system using the official corpus of Tweets for the NEEL 2016 Challenge.},
url = {http://ceur-ws.org/Vol-1691/paper_13.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 15:05 - 15:15 BEST NEEL SUBMISSION
Named Entity Linking in #Tweets with KEA
Jörg Waitelonis, Harald Sack
abstract
This paper presents the KEA system at the #Microposts 2016 NEEL Challenge. Its task is to recognize and type mentions from English microposts and link them to their corresponding entries in DBpedia 2014. For this task, we have adapted our Named Entity Disambiguation tool originally designed for natural language text to the special requirements of noisy, terse, and poorly worded tweets containing special functional terms and language.
bibtex
@InProceedings{{microposts2016_waitelonis,
author = {Waitelonis, Jorg and Sack, Harald},
title = {{Named Entity Linking in #tweets with KEA}},
crossref = {proc_microposts2016@www2016},
pages = {61--63},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {This paper presents the KEA system at the #Microposts 2016 NEEL Challenge. Its task is to recognize and type mentions from English microposts and link them to their corresponding entries in DBpedia 2014. For this task, we have adapted our Named Entity Disambiguation tool originally designed for natural language text to the special requirements of noisy, terse, and poorly worded tweets containing special functional terms and language.},
url = {http://ceur-ws.org/Vol-1691/paper_14.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 15:15 - 15:25
A Reverse Approach to Named Entity Extraction and Linking in Microposts
Kara Greenfield, Rajmonda Caceres, Michael Coury, Kelly Geyer, Youngjune Gwon, Jason Matterer, Alyssa Mensch, Cem Sahin, Olga Simek
abstract
In this paper, we present a pipeline for named entity extraction and linking that is designed specifically for noisy, grammatically inconsistent domains where traditional named entity techniques perform poorly. Our approach leverages a large knowledge base to improve entity recognition, while maintaining the use of traditional NER to identify mentions that are not co-referent with any entities in the knowledge base.
bibtex
@InProceedings{{microposts2016_greenfield,
author = {Greenfield, Kara and Caceres, Rajmonda and Coury, Michael and Geyer, Kelly and Gwon, Youngjune and Matterer, Jason and Mensch, Alyssa and Sahin, Cem and Simek, Olga},
title = {{A Reverse Approach to Named Entity Extraction and Linking in Microposts}},
crossref = {proc_microposts2016@www2016},
pages = {67--69},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {In this paper, we present a pipeline for named entity extraction and linking that is designed specifically for noisy, grammatically inconsistent domains where traditional named entity techniques perform poorly. Our approach leverages a large knowledge base to improve entity recognition, while maintaining the use of traditional NER to identify mentions that are not co-referent with any entities in the knowledge base.},
url = {http://ceur-ws.org/Vol-1691/paper_11.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
- 15:25 - 15:30
Feature Based Approach to Named Entity Recognition and Linking for Tweets
Souvick Ghosh, Promita Maitra, Dipankar Das
abstract
In this paper, we describe our approach for Named Entity Recognition and Linking Challenge (NEEL) at the #Microposts2016. The task is to automatically recognize entities and their types from English microposts, and link them to corresponding DBPedia 2015 entries. If the resources do not exist, we use NIL identifiers instead. The task is unique as twitter data is informal in nature with non-conformational spellings, random contractions and various other noises. For this task, we developed our system using a hybrid model. We have used various existing named entity recognition (NER) systems and combined them with our classifier to improve the results.
bibtex
@InProceedings{{microposts2016_ghosh,
author = {Ghosh, Souvick and Maitra, Promita and Das, Dipankar},
title = {{Feature Based Approach to Named Entity Recognition and Linking for Tweets }},
crossref = {proc_microposts2016@www2016},
pages = {74--76},
booktitle = {6th Workshop on Making Sense of Microposts {(\#Microposts2016)}},
year = 2016,
abstract = {In this paper, we describe our approach for Named Entity Recognition and Linking Challenge (NEEL) at the #Microposts2016. The task is to automatically recognize entities and their types from English microposts, and link them to corresponding DBPedia 2015 entries. If the resources do not exist, we use NIL identifiers instead. The task is unique as twitter data is informal in nature with non-conformational spellings, random contractions and various other noises. For this task, we developed our system using a hybrid model. We have used various existing named entity recognition (NER) systems and combined them with our classifier to improve the results.},
url = {http://ceur-ws.org/Vol-1691/paper_10.pdf},
}
@Proceedings{proc_microposts2016@www2016,
title = {Proceedings, 6th Workshop on Making Sense of Microposts {(\#Microposts2016)}: Big things come in small packages, Montreal, Canada, 11th of April 2016},
year = 2016,
booktitle = {Making Sense of Microposts {(\#Microposts2016)}},
editor = {Dadzie, Aba-Sah and Preo\c{t}iuc-Pietro, Daniel and Radovanovic, Danica and Cano Basave, Amparo E. and Weller, Katrin},
url = {http://ceur-ws.org/Vol-1691/},
}
